import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error
import math

def main():
    df_train = pd.read_csv("train.csv")
    df_test = pd.read_csv("test.csv")

    df_train[["gap", "smiles"]].to_csv("train_gap.csv")
    df_test[["smiles"]].to_csv("test_gap.csv")

main()